AES E-Library

F. Seipel, and A. Lerch, "Multi-Track Crosstalk Reduction Using Spectral Subtraction," Paper 10013, (2018 May.). doi: F. Seipel, and A. Lerch, "Multi-Track Crosstalk Reduction Using Spectral Subtraction," Paper 10013, (2018 May.). doi:
Abstract: While many music-related blind source separation methods focus on mono or stereo material, the detection and reduction of crosstalk in multi-track recordings is less researched. Crosstalk or “bleed” of one recorded channel in another is a very common phenomenon in specific genres such as jazz and classical, where all instrumentalists are recorded simultaneously. We present an efficient algorithm that estimates the crosstalk amount in the spectral domain and applies spectral subtraction to remove it. Randomly generated artificial mixtures from various anechoic orchestral source material were employed to develop and evaluate the algorithm, which scores an average SIR-Gain result of 15.14 dB on various datasets with different amounts of simulated crosstalk.

@article{seipel2018multi-track,
author={seipel, fabian and lerch, alexander},
journal={journal of the audio engineering society},
title={multi-track crosstalk reduction using spectral subtraction},
year={2018},
volume={},
number={},
pages={},
doi={},
month={may},} @article{seipel2018multi-track,
author={seipel, fabian and lerch, alexander},
journal={journal of the audio engineering society},
title={multi-track crosstalk reduction using spectral subtraction},
year={2018},
volume={},
number={},
pages={},
doi={},
month={may},
abstract={while many music-related blind source separation methods focus on mono or stereo material, the detection and reduction of crosstalk in multi-track recordings is less researched. crosstalk or “bleed” of one recorded channel in another is a very common phenomenon in specific genres such as jazz and classical, where all instrumentalists are recorded simultaneously. we present an efficient algorithm that estimates the crosstalk amount in the spectral domain and applies spectral subtraction to remove it. randomly generated artificial mixtures from various anechoic orchestral source material were employed to develop and evaluate the algorithm, which scores an average sir-gain result of 15.14 db on various datasets with different amounts of simulated crosstalk.},}

TY - paper
TI - Multi-Track Crosstalk Reduction Using Spectral Subtraction
SP - EP -
AU - Seipel, Fabian
AU - Lerch, Alexander
PY - 2018
JO - Journal of the Audio Engineering Society
IS -
VO -
VL -
Y1 - May 2018 TY - paper
TI - Multi-Track Crosstalk Reduction Using Spectral Subtraction
SP - EP -
AU - Seipel, Fabian
AU - Lerch, Alexander
PY - 2018
JO - Journal of the Audio Engineering Society
IS -
VO -
VL -
Y1 - May 2018
AB - While many music-related blind source separation methods focus on mono or stereo material, the detection and reduction of crosstalk in multi-track recordings is less researched. Crosstalk or “bleed” of one recorded channel in another is a very common phenomenon in specific genres such as jazz and classical, where all instrumentalists are recorded simultaneously. We present an efficient algorithm that estimates the crosstalk amount in the spectral domain and applies spectral subtraction to remove it. Randomly generated artificial mixtures from various anechoic orchestral source material were employed to develop and evaluate the algorithm, which scores an average SIR-Gain result of 15.14 dB on various datasets with different amounts of simulated crosstalk.